
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import matplotlib.pylab as plt
import seaborn as sns
%matplotlib inline


import os


os.getcwd()

'C:\\Users\\hp'


os.chdir('C:\\Users\\hp\\Documents')


os.getcwd()

'C:\\Users\\hp\\Documents'


df = pd.read_csv('datasets_11167_15520_train.csv')

df


df.head()


df.tail()


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2000 entries, 0 to 1999
Data columns (total 21 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   battery_power  2000 non-null   int64  
 1   blue           2000 non-null   int64  
 2   clock_speed    2000 non-null   float64
 3   dual_sim       2000 non-null   int64  
 4   fc             2000 non-null   int64  
 5   four_g         2000 non-null   int64  
 6   int_memory     2000 non-null   int64  
 7   m_dep          2000 non-null   float64
 8   mobile_wt      2000 non-null   int64  
 9   n_cores        2000 non-null   int64  
 10  pc             2000 non-null   int64  
 11  px_height      2000 non-null   int64  
 12  px_width       2000 non-null   int64  
 13  ram            2000 non-null   int64  
 14  sc_h           2000 non-null   int64  
 15  sc_w           2000 non-null   int64  
 16  talk_time      2000 non-null   int64  
 17  three_g        2000 non-null   int64  
 18  touch_screen   2000 non-null   int64  
 19  wifi           2000 non-null   int64  
 20  price_range    2000 non-null   int64  
dtypes: float64(2), int64(19)
memory usage: 328.2 KB


df.columns

Index(['battery_power', 'blue', 'clock_speed', 'dual_sim', 'fc', 'four_g',
       'int_memory', 'm_dep', 'mobile_wt', 'n_cores', 'pc', 'px_height',
       'px_width', 'ram', 'sc_h', 'sc_w', 'talk_time', 'three_g',
       'touch_screen', 'wifi', 'price_range'],
      dtype='object')


import sweetviz as sv
my_report = sv.analyze(df)
my_report.show_html()

Report SWEETVIZ_REPORT.html was generated! NOTEBOOK/COLAB USERS: the web browser MAY not pop up, regardless, the report IS saved in your notebook/colab files.


sns.boxplot(x='price_range',y='battery_power', data=df)

<AxesSubplot:xlabel='price_range', ylabel='battery_power'>


sns.boxplot(x='price_range',y='mobile_wt', data=df)

<AxesSubplot:xlabel='price_range', ylabel='mobile_wt'>


sns.boxplot(x='price_range',y='int_memory', data=df)

<AxesSubplot:xlabel='price_range', ylabel='int_memory'>


sns.boxplot(x='price_range',y='pc', data=df)

<AxesSubplot:xlabel='price_range', ylabel='pc'>


df.head()


df.hist(bins=20, figsize=(40,40))

array([[<AxesSubplot:title={'center':'battery_power'}>,
        <AxesSubplot:title={'center':'blue'}>,
        <AxesSubplot:title={'center':'clock_speed'}>,
        <AxesSubplot:title={'center':'dual_sim'}>,
        <AxesSubplot:title={'center':'fc'}>],
       [<AxesSubplot:title={'center':'four_g'}>,
        <AxesSubplot:title={'center':'int_memory'}>,
        <AxesSubplot:title={'center':'m_dep'}>,
        <AxesSubplot:title={'center':'mobile_wt'}>,
        <AxesSubplot:title={'center':'n_cores'}>],
       [<AxesSubplot:title={'center':'pc'}>,
        <AxesSubplot:title={'center':'px_height'}>,
        <AxesSubplot:title={'center':'px_width'}>,
        <AxesSubplot:title={'center':'ram'}>,
        <AxesSubplot:title={'center':'sc_h'}>],
       [<AxesSubplot:title={'center':'sc_w'}>,
        <AxesSubplot:title={'center':'talk_time'}>,
        <AxesSubplot:title={'center':'three_g'}>,
        <AxesSubplot:title={'center':'touch_screen'}>,
        <AxesSubplot:title={'center':'wifi'}>],
       [<AxesSubplot:title={'center':'price_range'}>, <AxesSubplot:>,
        <AxesSubplot:>, <AxesSubplot:>, <AxesSubplot:>]], dtype=object)


sns.pairplot(df,hue='price_range')

<seaborn.axisgrid.PairGrid at 0x20a806b0850>


df.isnull().sum()

battery_power    0
blue             0
clock_speed      0
dual_sim         0
fc               0
four_g           0
int_memory       0
m_dep            0
mobile_wt        0
n_cores          0
pc               0
px_height        0
px_width         0
ram              0
sc_h             0
sc_w             0
talk_time        0
three_g          0
touch_screen     0
wifi             0
price_range      0
dtype: int64


df.info()

<class 'pandas.core.frame.DataFrame'>
RangeIndex: 2000 entries, 0 to 1999
Data columns (total 21 columns):
 #   Column         Non-Null Count  Dtype  
---  ------         --------------  -----  
 0   battery_power  2000 non-null   int64  
 1   blue           2000 non-null   int64  
 2   clock_speed    2000 non-null   float64
 3   dual_sim       2000 non-null   int64  
 4   fc             2000 non-null   int64  
 5   four_g         2000 non-null   int64  
 6   int_memory     2000 non-null   int64  
 7   m_dep          2000 non-null   float64
 8   mobile_wt      2000 non-null   int64  
 9   n_cores        2000 non-null   int64  
 10  pc             2000 non-null   int64  
 11  px_height      2000 non-null   int64  
 12  px_width       2000 non-null   int64  
 13  ram            2000 non-null   int64  
 14  sc_h           2000 non-null   int64  
 15  sc_w           2000 non-null   int64  
 16  talk_time      2000 non-null   int64  
 17  three_g        2000 non-null   int64  
 18  touch_screen   2000 non-null   int64  
 19  wifi           2000 non-null   int64  
 20  price_range    2000 non-null   int64  
dtypes: float64(2), int64(19)
memory usage: 328.2 KB


df.columns

Index(['battery_power', 'blue', 'clock_speed', 'dual_sim', 'fc', 'four_g',
       'int_memory', 'm_dep', 'mobile_wt', 'n_cores', 'pc', 'px_height',
       'px_width', 'ram', 'sc_h', 'sc_w', 'talk_time', 'three_g',
       'touch_screen', 'wifi', 'price_range'],
      dtype='object')


plt.figure(figsize=(30,30), facecolor='white')
plotnumber = 1

for column in df:
    if plotnumber<20:
        ax=plt.subplot(20,2,plotnumber)
        sns.boxplot(x=df[column])
        plt.xlabel(column,fontsize=20)
    plotnumber+=1
plt.tight_layout()


sns.boxplot(df.fc)

C:\ProgramData\Anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='fc'>


from scipy import stats

IQR = stats.iqr(df.fc, interpolation = 'midpoint')

IQR

6.0


Q1 = df.fc.quantile(0.25)
Q3 = df.fc.quantile(0.75)
min = Q1-1.5*IQR
max = Q3+1.5*IQR

min

-8.0

max

16.0


len(df.loc[df['fc']>max])

18


df.shape

(2000, 21)


df.shape[0]
len(df.loc[df['fc']>max])
18/2000*100

0.8999999999999999


df.loc[df['fc']>max,'fc']=np.median(df.fc)


df.loc[df['fc']>max]


sns.boxplot(df.fc)

C:\ProgramData\Anaconda3\lib\site-packages\seaborn\_decorators.py:36: FutureWarning: Pass the following variable as a keyword arg: x. From version 0.12, the only valid positional argument will be `data`, and passing other arguments without an explicit keyword will result in an error or misinterpretation.
  warnings.warn(

<AxesSubplot:xlabel='fc'>


plt.figure(figsize=(25,25))
sns.heatmap(df.corr(), annot=True, cmap='cool')

<AxesSubplot:>


df.duplicated().sum()

0


df.describe()


df.isnull().sum()

battery_power    0
blue             0
clock_speed      0
dual_sim         0
fc               0
four_g           0
int_memory       0
m_dep            0
mobile_wt        0
n_cores          0
pc               0
px_height        0
px_width         0
ram              0
sc_h             0
sc_w             0
talk_time        0
three_g          0
touch_screen     0
wifi             0
price_range      0
dtype: int64


x = df.drop(columns = ['price_range'],axis=1)
y = df['price_range']

x

y

0       1
1       2
2       2
3       2
4       1
       ..
1995    0
1996    2
1997    3
1998    0
1999    3
Name: price_range, Length: 2000, dtype: int64


## Standard removes the mean and scales each feature/variable to unit variance

from sklearn.preprocessing import StandardScaler
scaler = StandardScaler()
x_scaled = scaler.fit_transform(x)


x_scaled

array([[-0.90259726, -0.9900495 ,  0.83077942, ..., -1.78686097,
        -1.00601811,  0.98609664],
       [-0.49513857,  1.0100505 , -1.2530642 , ...,  0.55964063,
         0.99401789, -1.01409939],
       [-1.5376865 ,  1.0100505 , -1.2530642 , ...,  0.55964063,
         0.99401789, -1.01409939],
       ...,
       [ 1.53077336, -0.9900495 , -0.76274805, ...,  0.55964063,
         0.99401789, -1.01409939],
       [ 0.62252745, -0.9900495 , -0.76274805, ...,  0.55964063,
         0.99401789,  0.98609664],
       [-1.65833069,  1.0100505 ,  0.58562134, ...,  0.55964063,
         0.99401789,  0.98609664]])


## creating traing and testing data
from sklearn.model_selection import train_test_split
x_train,x_test,y_train,y_test = train_test_split(X_scaled,y, test_size= 0.20, random_state=0)


##Model creation

from sklearn.linear_model import LogisticRegression
lreg  = LogisticRegression()
lreg.fit(x_train, y_train)

LogisticRegression()

LogisticRegression()


y_pred = lreg.predict(x_test)


y_pred_test = lreg.predict(x_test)
y_pred_train = lreg.predict(x_train)


from sklearn.metrics import accuracy_score, confusion_matrix, roc_auc_score,precision_score, recall_score, f1_score, classification_report
report=classification_report(y_test,y_pred)
print(report)

              precision    recall  f1-score   support

           0       0.98      0.98      0.98        95
           1       0.94      0.92      0.93        92
           2       0.94      0.92      0.93        99
           3       0.96      0.99      0.97       114

    accuracy                           0.95       400
   macro avg       0.95      0.95      0.95       400
weighted avg       0.95      0.95      0.95       400


y_pred_test

array([3, 0, 2, 2, 3, 0, 0, 3, 3, 1, 1, 3, 0, 2, 3, 0, 3, 2, 2, 1, 0, 0,
       3, 1, 2, 2, 3, 1, 3, 1, 1, 0, 2, 0, 2, 3, 0, 0, 3, 3, 3, 1, 3, 3,
       1, 3, 0, 1, 3, 1, 1, 3, 0, 3, 0, 2, 2, 2, 0, 3, 3, 1, 3, 2, 1, 2,
       3, 2, 2, 2, 3, 2, 1, 0, 1, 3, 2, 2, 1, 2, 3, 3, 3, 0, 0, 0, 2, 1,
       2, 3, 1, 2, 2, 1, 0, 3, 3, 3, 0, 3, 1, 1, 3, 1, 3, 2, 2, 3, 2, 3,
       3, 0, 0, 1, 3, 3, 0, 0, 1, 0, 0, 3, 2, 2, 1, 2, 1, 1, 0, 2, 1, 3,
       3, 3, 3, 3, 3, 2, 0, 1, 1, 2, 1, 3, 0, 3, 0, 0, 2, 0, 1, 1, 1, 1,
       3, 0, 0, 3, 1, 3, 2, 1, 3, 1, 2, 3, 3, 2, 1, 0, 3, 1, 2, 3, 3, 0,
       2, 2, 3, 1, 2, 1, 0, 1, 2, 2, 2, 0, 3, 3, 1, 1, 0, 2, 3, 0, 1, 2,
       2, 0, 3, 3, 3, 1, 2, 3, 3, 3, 0, 0, 0, 2, 3, 3, 0, 0, 1, 3, 2, 3,
       3, 3, 0, 0, 2, 3, 3, 1, 0, 2, 0, 0, 0, 3, 2, 1, 2, 2, 1, 1, 0, 2,
       3, 3, 0, 0, 1, 3, 3, 1, 3, 0, 3, 1, 1, 0, 2, 3, 3, 2, 0, 0, 1, 2,
       3, 2, 2, 3, 2, 1, 0, 3, 3, 2, 1, 3, 2, 2, 2, 1, 0, 2, 2, 1, 0, 0,
       2, 2, 2, 3, 0, 1, 3, 0, 2, 2, 3, 0, 2, 0, 1, 1, 3, 0, 0, 2, 3, 1,
       2, 0, 2, 0, 3, 0, 3, 3, 2, 3, 1, 2, 2, 1, 1, 1, 0, 1, 0, 3, 1, 0,
       3, 0, 0, 1, 3, 0, 3, 1, 1, 0, 1, 3, 0, 2, 1, 1, 2, 1, 1, 0, 2, 0,
       0, 3, 1, 2, 3, 2, 2, 0, 3, 2, 2, 1, 3, 2, 3, 3, 3, 0, 2, 0, 3, 0,
       1, 1, 2, 3, 1, 3, 1, 2, 0, 1, 2, 3, 0, 0, 1, 3, 0, 3, 0, 2, 2, 1,
       1, 0, 2, 0], dtype=int64)


y_train.shape

(1600,)


y_pred.shape

(400,)


## Calculating accuracy

from sklearn.metrics import accuracy_score, confusion_matrix, precision_score, recall_score, f1_score, classification_report
accuracy = accuracy_score(y_test, y_pred)*100
print('Accuracy of the Logistic Model :', accuracy)

Accuracy of the Logistic Model : 95.5


test_accuracy = accuracy_score(y_test, y_pred)*100
print('Test accuracy score :', test_accuracy)

Test accuracy score : 95.5


## classification report on test data
report=classification_report(y_test,y_pred)
print(report)

              precision    recall  f1-score   support

           0       0.98      0.98      0.98        95
           1       0.94      0.92      0.93        92
           2       0.94      0.92      0.93        99
           3       0.96      0.99      0.97       114

    accuracy                           0.95       400
   macro avg       0.95      0.95      0.95       400
weighted avg       0.95      0.95      0.95       400


#Classification on train data
report=classification_report(y_pred_train,y_train)
print(report)

              precision    recall  f1-score   support

           0       0.99      0.98      0.99       409
           1       0.97      0.97      0.97       410
           2       0.97      0.98      0.97       395
           3       0.99      0.99      0.99       386

    accuracy                           0.98      1600
   macro avg       0.98      0.98      0.98      1600
weighted avg       0.98      0.98      0.98      1600


train_roc_auc_score = roc_auc_score(y_train, lreg.predict_proba(x_train), multi_class='ovr')
test_roc_auc_score = roc_auc_score(y_test, lreg.predict_proba(x_test), multi_class='ovr')
print("The ROC AUC score on the train data is: ", train_roc_auc_score)
print("The ROC AUC score on the test data is: ", test_roc_auc_score)

The ROC AUC score on the train data is:  0.9993970468561584
The ROC AUC score on the test data is:  0.9974567399972236


from sklearn .svm import SVC
svm_clf = SVC(probability=True)
svm_clf.fit(x_train, y_train)

SVC(probability=True)

SVC(probability=True)


y_pred_train = svm_clf.predict(x_train)
y_pred_test = svm_clf.predict(x_test)


print('Train Accuracy:'+str(accuracy_score(y_pred_train,y_train)*100))
print('Test Accuracy:'+str(accuracy_score(y_pred_test,y_test)*100))
print('\nConfusion Matrix:\n%s'%confusion_matrix(y_pred_test,y_test))

Train Accuracy:98.1875
Test Accuracy:88.25

Confusion Matrix:
[[ 89   4   0   0]
 [  6  81  14   0]
 [  0   7  81  12]
 [  0   0   4 102]]


print('train accuracy:',svm_clf.score(x_train,y_train))
print('test accuracy:',svm_clf.score(x_test,y_test))

train accuracy: 0.981875
test accuracy: 0.8825


train_roc_auc_score = roc_auc_score(y_train,  svm_clf.predict_proba(x_train), multi_class='ovr')
test_roc_auc_score = roc_auc_score(y_test,  svm_clf.predict_proba(x_test), multi_class='ovr')
print("The ROC AUC score on the train data is: ", train_roc_auc_score)
print("The ROC AUC score on the test data is: ", test_roc_auc_score)

The ROC AUC score on the train data is:  0.9995552907707126
The ROC AUC score on the test data is:  0.9878584289660093


from sklearn.metrics import accuracy_score, confusion_matrix,roc_auc_score, classification_report
from sklearn.tree import DecisionTreeClassifier


# creating object of the decision tree.

dtc=DecisionTreeClassifier(max_depth = 5)


dtc.fit(x_train, y_train)

DecisionTreeClassifier(max_depth=5)

DecisionTreeClassifier(max_depth=5)


y_pred_train = dtc.predict(x_train)
y_pred = dtc.predict(x_test)


## checking train set accuracy

accuracy_score(y_train,y_pred_train)

0.878125


## checking test set accuracy
accuracy_score(y_test,y_pred)

0.8275


## Confusion matrix  for set data
cf_matrix= confusion_matrix(y_test,y_pred)
cf_matrix

array([[ 87,   8,   0,   0],
       [  6,  79,   7,   0],
       [  0,  21,  60,  18],
       [  0,   0,   9, 105]], dtype=int64)


## Printing classification of train set
print(classification_report(y_train,y_pred_train))

              precision    recall  f1-score   support

           0       0.94      0.94      0.94       405
           1       0.80      0.91      0.85       408
           2       0.88      0.73      0.80       401
           3       0.90      0.94      0.92       386

    accuracy                           0.88      1600
   macro avg       0.88      0.88      0.88      1600
weighted avg       0.88      0.88      0.88      1600


## printing classification of test set
print(classification_report(y_test,y_pred))

              precision    recall  f1-score   support

           0       0.94      0.92      0.93        95
           1       0.73      0.86      0.79        92
           2       0.79      0.61      0.69        99
           3       0.85      0.92      0.89       114

    accuracy                           0.83       400
   macro avg       0.83      0.83      0.82       400
weighted avg       0.83      0.83      0.82       400


## creating an object of classifier

dtc= DecisionTreeClassifier(random_state=0)


from sklearn.model_selection import GridSearchCV


dtc = DecisionTreeClassifier(max_depth = 5)
dtc.fit(x_train, y_train)

DecisionTreeClassifier(max_depth=5)

DecisionTreeClassifier(max_depth=5)


grid = GridSearchCV(dtc, param_grid = {'max_depth': (5, 30), 'max_leaf_nodes': (10, 100)}, scoring = 'accuracy', cv = 5, verbose = 24)
grid.fit(x_train, y_train)

Fitting 5 folds for each of 4 candidates, totalling 20 fits
[CV 1/5; 1/4] START max_depth=5, max_leaf_nodes=10..............................
[CV 1/5; 1/4] END max_depth=5, max_leaf_nodes=10;, score=0.794 total time=   0.0s
[CV 2/5; 1/4] START max_depth=5, max_leaf_nodes=10..............................
[CV 2/5; 1/4] END max_depth=5, max_leaf_nodes=10;, score=0.784 total time=   0.0s
[CV 3/5; 1/4] START max_depth=5, max_leaf_nodes=10..............................
[CV 3/5; 1/4] END max_depth=5, max_leaf_nodes=10;, score=0.775 total time=   0.0s
[CV 4/5; 1/4] START max_depth=5, max_leaf_nodes=10..............................
[CV 4/5; 1/4] END max_depth=5, max_leaf_nodes=10;, score=0.812 total time=   0.0s
[CV 5/5; 1/4] START max_depth=5, max_leaf_nodes=10..............................
[CV 5/5; 1/4] END max_depth=5, max_leaf_nodes=10;, score=0.825 total time=   0.0s
[CV 1/5; 2/4] START max_depth=5, max_leaf_nodes=100.............................
[CV 1/5; 2/4] END max_depth=5, max_leaf_nodes=100;, score=0.822 total time=   0.0s
[CV 2/5; 2/4] START max_depth=5, max_leaf_nodes=100.............................
[CV 2/5; 2/4] END max_depth=5, max_leaf_nodes=100;, score=0.791 total time=   0.0s
[CV 3/5; 2/4] START max_depth=5, max_leaf_nodes=100.............................
[CV 3/5; 2/4] END max_depth=5, max_leaf_nodes=100;, score=0.803 total time=   0.0s
[CV 4/5; 2/4] START max_depth=5, max_leaf_nodes=100.............................
[CV 4/5; 2/4] END max_depth=5, max_leaf_nodes=100;, score=0.816 total time=   0.0s
[CV 5/5; 2/4] START max_depth=5, max_leaf_nodes=100.............................
[CV 5/5; 2/4] END max_depth=5, max_leaf_nodes=100;, score=0.850 total time=   0.0s
[CV 1/5; 3/4] START max_depth=30, max_leaf_nodes=10.............................
[CV 1/5; 3/4] END max_depth=30, max_leaf_nodes=10;, score=0.794 total time=   0.0s
[CV 2/5; 3/4] START max_depth=30, max_leaf_nodes=10.............................
[CV 2/5; 3/4] END max_depth=30, max_leaf_nodes=10;, score=0.784 total time=   0.0s
[CV 3/5; 3/4] START max_depth=30, max_leaf_nodes=10.............................
[CV 3/5; 3/4] END max_depth=30, max_leaf_nodes=10;, score=0.775 total time=   0.0s
[CV 4/5; 3/4] START max_depth=30, max_leaf_nodes=10.............................
[CV 4/5; 3/4] END max_depth=30, max_leaf_nodes=10;, score=0.812 total time=   0.0s
[CV 5/5; 3/4] START max_depth=30, max_leaf_nodes=10.............................
[CV 5/5; 3/4] END max_depth=30, max_leaf_nodes=10;, score=0.825 total time=   0.0s
[CV 1/5; 4/4] START max_depth=30, max_leaf_nodes=100............................
[CV 1/5; 4/4] END max_depth=30, max_leaf_nodes=100;, score=0.828 total time=   0.0s
[CV 2/5; 4/4] START max_depth=30, max_leaf_nodes=100............................
[CV 2/5; 4/4] END max_depth=30, max_leaf_nodes=100;, score=0.838 total time=   0.0s
[CV 3/5; 4/4] START max_depth=30, max_leaf_nodes=100............................
[CV 3/5; 4/4] END max_depth=30, max_leaf_nodes=100;, score=0.809 total time=   0.0s
[CV 4/5; 4/4] START max_depth=30, max_leaf_nodes=100............................
[CV 4/5; 4/4] END max_depth=30, max_leaf_nodes=100;, score=0.828 total time=   0.0s
[CV 5/5; 4/4] START max_depth=30, max_leaf_nodes=100............................
[CV 5/5; 4/4] END max_depth=30, max_leaf_nodes=100;, score=0.819 total time=   0.0s

GridSearchCV(cv=5, estimator=DecisionTreeClassifier(max_depth=5),
             param_grid={'max_depth': (5, 30), 'max_leaf_nodes': (10, 100)},
             scoring='accuracy', verbose=24)

GridSearchCV(cv=5, estimator=DecisionTreeClassifier(max_depth=5),
             param_grid={'max_depth': (5, 30), 'max_leaf_nodes': (10, 100)},
             scoring='accuracy', verbose=24)

DecisionTreeClassifier(max_depth=5)

DecisionTreeClassifier(max_depth=5)


##Predicting y values of train and test set.
y_train_pred=dtc_optimal.predict(x_train)
y_pred=dtc_optimal.predict(x_test)


accuracy_score(y_train,y_train_pred)

0.96875


accuracy_score(y_test,y_pred)

0.85


#getting confusion matrix for test set

cf_matrix=confusion_matrix(y_test,y_pred)
cf_matrix

array([[ 87,   8,   0,   0],
       [  8,  76,   8,   0],
       [  0,  14,  75,  10],
       [  0,   0,  12, 102]], dtype=int64)


## printing Classification report for train set.
print(classification_report(y_train,y_train_pred))

              precision    recall  f1-score   support

           0       0.97      1.00      0.98       405
           1       0.98      0.94      0.96       408
           2       0.94      0.97      0.96       401
           3       0.99      0.97      0.98       386

    accuracy                           0.97      1600
   macro avg       0.97      0.97      0.97      1600
weighted avg       0.97      0.97      0.97      1600


##print classification report for test set
print(classification_report(y_test,y_pred))

              precision    recall  f1-score   support

           0       0.92      0.92      0.92        95
           1       0.78      0.83      0.80        92
           2       0.79      0.76      0.77        99
           3       0.91      0.89      0.90       114

    accuracy                           0.85       400
   macro avg       0.85      0.85      0.85       400
weighted avg       0.85      0.85      0.85       400


y_pred

array([3, 0, 2, 2, 2, 0, 0, 3, 3, 1, 0, 3, 0, 2, 3, 0, 3, 2, 2, 1, 0, 0,
       3, 1, 1, 1, 3, 1, 3, 1, 1, 0, 2, 1, 1, 3, 0, 0, 3, 3, 2, 1, 3, 2,
       1, 3, 0, 1, 3, 1, 1, 3, 0, 3, 0, 2, 2, 1, 0, 3, 3, 1, 3, 2, 1, 3,
       3, 2, 2, 2, 3, 2, 1, 0, 1, 3, 2, 2, 1, 2, 3, 3, 3, 0, 0, 0, 2, 1,
       2, 3, 1, 3, 2, 1, 0, 3, 2, 3, 0, 3, 2, 1, 3, 1, 3, 2, 2, 3, 2, 3,
       3, 0, 0, 1, 2, 2, 0, 0, 1, 0, 0, 3, 2, 2, 1, 2, 1, 1, 0, 2, 1, 3,
       2, 3, 3, 3, 3, 2, 0, 0, 1, 2, 2, 3, 1, 3, 0, 0, 2, 0, 0, 1, 2, 1,
       3, 1, 0, 3, 1, 3, 2, 1, 3, 1, 2, 3, 3, 2, 1, 0, 3, 2, 2, 2, 3, 0,
       2, 2, 3, 0, 3, 1, 0, 1, 3, 2, 2, 0, 2, 3, 1, 1, 0, 2, 3, 0, 1, 2,
       1, 0, 3, 3, 3, 1, 2, 3, 3, 3, 1, 0, 0, 2, 3, 3, 0, 0, 1, 3, 1, 3,
       3, 3, 0, 0, 2, 3, 3, 2, 0, 2, 0, 0, 0, 3, 3, 1, 2, 2, 0, 1, 0, 2,
       3, 3, 0, 0, 1, 3, 3, 1, 3, 0, 3, 1, 1, 0, 2, 3, 3, 2, 0, 0, 1, 2,
       3, 2, 2, 3, 1, 1, 1, 3, 2, 2, 1, 3, 2, 2, 2, 0, 0, 2, 2, 1, 0, 0,
       2, 2, 2, 2, 0, 1, 3, 0, 1, 2, 3, 0, 1, 0, 0, 1, 3, 0, 0, 2, 3, 0,
       1, 0, 2, 0, 3, 0, 3, 3, 2, 3, 1, 1, 2, 1, 1, 1, 0, 1, 0, 3, 1, 0,
       3, 1, 0, 1, 2, 0, 3, 1, 2, 0, 1, 3, 0, 2, 1, 1, 1, 1, 1, 0, 2, 0,
       1, 3, 1, 3, 3, 2, 1, 0, 3, 3, 1, 1, 2, 2, 3, 3, 3, 0, 2, 0, 3, 0,
       1, 1, 2, 3, 2, 3, 1, 1, 0, 1, 2, 2, 0, 1, 1, 3, 0, 3, 0, 2, 2, 1,
       0, 0, 3, 1], dtype=int64)


train_roc_auc_score = roc_auc_score(y_train,  dtc.predict_proba(x_train), multi_class='ovr')
test_roc_auc_score = roc_auc_score(y_test,  dtc.predict_proba(x_test), multi_class='ovr')
print("The ROC AUC score on the train data is: ", train_roc_auc_score)
print("The ROC AUC score on the test data is: ", test_roc_auc_score)

The ROC AUC score on the train data is:  0.9733775758403238
The ROC AUC score on the test data is:  0.9501624102057493


#fitting the data model 

from sklearn.ensemble import RandomForestClassifier
rfc = RandomForestClassifier(n_estimators = 100, random_state=0)
rfc.fit(x_train,y_train)

RandomForestClassifier(random_state=0)

RandomForestClassifier(random_state=0)


##{rediction on train and test data

random_y_train_pred=rfc.predict(x_train)
random_y_test_pred=rfc.predict(x_test)


from sklearn.metrics import accuracy_score, confusion_matrix, roc_auc_score, classification_report

# Get the accuracy scores

train_accuracy = accuracy_score(random_y_train_pred,y_train)
test_accuracy = accuracy_score(random_y_test_pred, y_test)


print("the accuracy on train data is :", train_accuracy)
print('The accuracy on test data is :', test_accuracy)
print('---'*20)
print('---'*20)

cm_train = confusion_matrix(random_y_train_pred,y_train)
cm_test = confusion_matrix(random_y_test_pred, y_test)

print('The confusion matrix on the train data os :')
print(cm_train)
print('')
print('The confusion matrix on the train data is :')
print(cm_test)
print('---'*20)
print('---'*20)

train_report = classification_report(random_y_train_pred, y_train)
test_report = classification_report(random_y_test_pred, y_test)
print('The classification report on the train data is :')
print(train_report)
print('')
print('The classification report on the test data is :')
print(test_report)
print('---'*20)
print('---'*20)

train_roc_auc_score = roc_auc_score(y_train, rfc.predict_proba(x_train), multi_class='ovr')
test_roc_auc_score = roc_auc_score(y_test, rfc.predict_proba(x_test),multi_class='ovr')
print('The ROC AUC score on the train data is: ', train_roc_auc_score)
print('The ROC AUC score on the test data is:', test_roc_auc_score)

the accuracy on train data is : 1.0
The accuracy on test data is : 0.845
------------------------------------------------------------
------------------------------------------------------------
The confusion matrix on the train data os :
[[405   0   0   0]
 [  0 408   0   0]
 [  0   0 401   0]
 [  0   0   0 386]]

The confusion matrix on the train data is :
[[ 93   7   0   0]
 [  2  73  18   0]
 [  0  12  68  10]
 [  0   0  13 104]]
------------------------------------------------------------
------------------------------------------------------------
The classification report on the train data is :
              precision    recall  f1-score   support

           0       1.00      1.00      1.00       405
           1       1.00      1.00      1.00       408
           2       1.00      1.00      1.00       401
           3       1.00      1.00      1.00       386

    accuracy                           1.00      1600
   macro avg       1.00      1.00      1.00      1600
weighted avg       1.00      1.00      1.00      1600


The classification report on the test data is :
              precision    recall  f1-score   support

           0       0.98      0.93      0.95       100
           1       0.79      0.78      0.79        93
           2       0.69      0.76      0.72        90
           3       0.91      0.89      0.90       117

    accuracy                           0.84       400
   macro avg       0.84      0.84      0.84       400
weighted avg       0.85      0.84      0.85       400

------------------------------------------------------------
------------------------------------------------------------
The ROC AUC score on the train data is:  1.0
The ROC AUC score on the test data is: 0.9747061873661376


## Splitiing the data into train test split.
x_train,x_test, y_train,y_test = train_test_split(X,y, test_size=0.2, random_state=0)


from sklearn.metrics import accuracy_score, classification_report, plot_confusion_matrix,confusion_matrix,roc_curve,roc_auc_score,auc
from xgboost import XGBClassifier


xgb=XGBClassifier()
xgb.fit(x_train, y_train)

XGBClassifier(base_score=0.5, booster='gbtree', callbacks=None,
              colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,
              early_stopping_rounds=None, enable_categorical=False,
              eval_metric=None, gamma=0, gpu_id=-1, grow_policy='depthwise',
              importance_type=None, interaction_constraints='',
              learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,
              max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,
              missing=nan, monotone_constraints='()', n_estimators=100,
              n_jobs=0, num_parallel_tree=1, objective='multi:softprob',
              predictor='auto', random_state=0, reg_alpha=0, ...)

XGBClassifier(base_score=0.5, booster='gbtree', callbacks=None,
              colsample_bylevel=1, colsample_bynode=1, colsample_bytree=1,
              early_stopping_rounds=None, enable_categorical=False,
              eval_metric=None, gamma=0, gpu_id=-1, grow_policy='depthwise',
              importance_type=None, interaction_constraints='',
              learning_rate=0.300000012, max_bin=256, max_cat_to_onehot=4,
              max_delta_step=0, max_depth=6, max_leaves=0, min_child_weight=1,
              missing=nan, monotone_constraints='()', n_estimators=100,
              n_jobs=0, num_parallel_tree=1, objective='multi:softprob',
              predictor='auto', random_state=0, reg_alpha=0, ...)


# predicting values of train and test data.
y_train_pred = xgb.predict(x_train)
y_pred=xgb.predict(x_test)


## checking the accuracy score of train set

accuracy_score(y_train,y_train_pred)

1.0


## checking the accuracy score of test data
accuracy_score(y_test,y_pred)

0.905


## confusion  matrix
cf_matrix = confusion_matrix(y_test,y_pred)
cf_matrix

array([[ 93,   2,   0,   0],
       [  3,  82,   7,   0],
       [  0,   8,  81,  10],
       [  0,   0,   8, 106]], dtype=int64)


##printing the classification report of train set
print(classification_report(y_train,y_train_pred))

              precision    recall  f1-score   support

           0       1.00      1.00      1.00       405
           1       1.00      1.00      1.00       408
           2       1.00      1.00      1.00       401
           3       1.00      1.00      1.00       386

    accuracy                           1.00      1600
   macro avg       1.00      1.00      1.00      1600
weighted avg       1.00      1.00      1.00      1600


## printing the classification report of test set
print(classification_report(y_test,y_pred))

              precision    recall  f1-score   support

           0       0.97      0.98      0.97        95
           1       0.89      0.89      0.89        92
           2       0.84      0.82      0.83        99
           3       0.91      0.93      0.92       114

    accuracy                           0.91       400
   macro avg       0.90      0.90      0.90       400
weighted avg       0.90      0.91      0.90       400


train_roc_auc_score = roc_auc_score(y_train,  xgb.predict_proba(x_train), multi_class='ovr')
test_roc_auc_score = roc_auc_score(y_test,  xgb.predict_proba(x_test), multi_class='ovr')
print("The ROC AUC score on the train data is: ", train_roc_auc_score)
print("The ROC AUC score on the test data is: ", test_roc_auc_score)

The ROC AUC score on the train data is:  1.0
The ROC AUC score on the test data is:  0.9907696704569308


Comparision_dict={'Model Name':['Logistic regression','Support Vector Machine', 'Decision Tree Classifier','Random Forest Classifier','XGboost regression'],
                 'Training_ Accuracy':[0.98,0.981875,0.97,1.00,1.0],
                 'Test_Accuracy':[0.95,0.8825,0.85,0.845,0.91],
                 'Train_roc_auc_score':[0.99939,0.9995,1.0,1.0,1.0],
                 'Test_roc_auc_score':[0.9974,0.9877,0.8838,0.9747,0.9747]}


comparisione_df=pd.DataFrame(Comparision_dict)


comparisione_df

	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	...	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi	price_range
count	2000.000000	2000.0000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	...	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000	2000.000000
mean	1238.518500	0.4950	1.522250	0.509500	4.177000	0.521500	32.046500	0.501750	140.249000	4.520500	...	645.108000	1251.515500	2124.213000	12.306500	5.767000	11.011000	0.761500	0.503000	0.507000	1.500000
std	439.418206	0.5001	0.816004	0.500035	4.150094	0.499662	18.145715	0.288416	35.399655	2.287837	...	443.780811	432.199447	1084.732044	4.213245	4.356398	5.463955	0.426273	0.500116	0.500076	1.118314
min	501.000000	0.0000	0.500000	0.000000	0.000000	0.000000	2.000000	0.100000	80.000000	1.000000	...	0.000000	500.000000	256.000000	5.000000	0.000000	2.000000	0.000000	0.000000	0.000000	0.000000
25%	851.750000	0.0000	0.700000	0.000000	1.000000	0.000000	16.000000	0.200000	109.000000	3.000000	...	282.750000	874.750000	1207.500000	9.000000	2.000000	6.000000	1.000000	0.000000	0.000000	0.750000
50%	1226.000000	0.0000	1.500000	1.000000	3.000000	1.000000	32.000000	0.500000	141.000000	4.000000	...	564.000000	1247.000000	2146.500000	12.000000	5.000000	11.000000	1.000000	1.000000	1.000000	1.500000
75%	1615.250000	1.0000	2.200000	1.000000	7.000000	1.000000	48.000000	0.800000	170.000000	7.000000	...	947.250000	1633.000000	3064.500000	16.000000	9.000000	16.000000	1.000000	1.000000	1.000000	2.250000
max	1998.000000	1.0000	3.000000	1.000000	16.000000	1.000000	64.000000	1.000000	200.000000	8.000000	...	1960.000000	1998.000000	3998.000000	19.000000	18.000000	20.000000	1.000000	1.000000	1.000000	3.000000

Cellphone Price Prediction¶

Business Case¶

Exploratory Data Analysis¶

Data Preprocessing¶

Handling outliers¶

Feature selection¶

Model Creation¶

Logistic Regression¶

There are two possibilities from here :¶

SVM¶

Here we can excellent result obtained by SVM¶

Decision Tree Classifier¶

Let's tune some hyperparameters of decision tree classifier:¶

Decision Tree classifier-Observation¶

Random Forest¶

Evaluation metrcis¶

Here we can see our model is overfitted so we are moving to next algirithm¶

XGBoost Classifier¶

with default hyperparameters¶

Comparision¶

As above we can see Random forest classifier and XGboost models are overfitted hence we are putting two models out of consideration¶

Conclusion¶

	battery_power	blue	clock_speed	dual_sim	fc	four_g	int_memory	m_dep	mobile_wt	n_cores	...	px_height	px_width	ram	sc_h	sc_w	talk_time	three_g	touch_screen	wifi	price_range
0	842	0	2.2	0	1	0	7	0.6	188	2	...	20	756	2549	9	7	19	0	0	1	1
1	1021	1	0.5	1	0	1	53	0.7	136	3	...	905	1988	2631	17	3	7	1	1	0	2
2	563	1	0.5	1	2	1	41	0.9	145	5	...	1263	1716	2603	11	2	9	1	1	0	2
3	615	1	2.5	0	0	0	10	0.8	131	6	...	1216	1786	2769	16	8	11	1	0	0	2
4	1821	1	1.2	0	13	1	44	0.6	141	2	...	1208	1212	1411	8	2	15	1	1	0	1
...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...	...
1995	794	1	0.5	1	0	1	2	0.8	106	6	...	1222	1890	668	13	4	19	1	1	0	0
1996	1965	1	2.6	1	0	0	39	0.2	187	4	...	915	1965	2032	11	10	16	1	1	1	2
1997	1911	0	0.9	1	1	1	36	0.7	108	8	...	868	1632	3057	9	1	5	1	1	0	3
1998	1512	0	0.9	0	4	1	46	0.1	145	5	...	336	670	869	18	10	19	1	1	1	0
1999	510	1	2.0	1	5	1	45	0.9	168	6	...	483	754	3919	19	4	2	1	1	1	3

	Model Name	Training_ Accuracy	Test_Accuracy	Train_roc_auc_score	Test_roc_auc_score
0	Logistic regression	0.980000	0.9500	0.99939	0.9974
1	Support Vector Machine	0.981875	0.8825	0.99950	0.9877
2	Decision Tree Classifier	0.970000	0.8500	1.00000	0.8838
3	Random Forest Classifier	1.000000	0.8450	1.00000	0.9747
4	XGboost regression	1.000000	0.9100	1.00000	0.9747